© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16769
    Prev
    Next
    INDEX
    Explanations

    ancillary, talus, Court, collection, Article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĤĨæĹłå¿Į
    -0.08
    viol
    -0.07
    eny
    -0.06
    kehr
    -0.06
     Vel
    -0.06
    éħ¸åĮĸ
    -0.06
    weiler
    -0.06
    EE
    -0.06
    erings
    -0.06
    agation
    -0.06
    POSITIVE LOGITS
    retti
    0.08
    ogan
    0.08
    ocere
    0.08
    ofile
    0.07
     Apel
    0.07
    æĺ
    0.07
    imt
    0.07
    ophobic
    0.07
    edig
    0.07
    avl
    0.07
    Activations Density 0.121%

    No Known Activations